MMMU-Pro
Emerging14papers using it
2024first seen
MMMU-Pro (A More Robust Multi-discipline Multimodal Understanding Benchmark) 🌐 Homepage | 🏆 Leaderboard | 🤗 Dataset | 🤗 Paper | 📖 arXiv | GitHub 🔔News 🛠️[2026-05-30] Fixed the option augmentation issue in Vision and Standard (10 options) settings. (validation_Diagnostics_and_Laboratory_Medicine_17) 🛠️[2025-03-0
Papers using MMMU-Pro (14)
- Xiaomi Mimo-vl-miloco Technical ReportOmniThoughtVis: A Scalable Distillation Pipeline for Deployable Multimodal Reasoning ModelsVLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language ModelsVision Verification Enhanced Fusion of VLMs for Efficient Visual ReasoningVOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy DistillationSocratic-MCTS: Test-Time Visual Reasoning by Asking the Right QuestionsBelieving Without Seeing: Quality Scores For Contextualizing Vision-language Model ExplanationsJmmmu-pro: Image-based Japanese Multi-discipline Multimodal Understanding Benchmark Via Vibe Benchmark ConstructionSRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement LearningVisualWebInstruct: Scaling up Multimodal Instruction Data through Web
SearchChain-of-Description: What I can understand, I can put into wordsMMMU-Pro: A More Robust Multi-discipline Multimodal Understanding BenchmarkVL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward ModelsMAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale